INDEX

Explanations

json structure keys

This neuron consistently lights up on specific named entities or rare technical terms—particularly proper names (e.g. color‐pigment names like “Manganese Violet” or “Blue 1 Lake”), user names, or other distinctive proper nouns.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 dwóch

0.57

 вторая

0.54

 তড়িৎ

0.54

 याता

0.52

sixth

0.52

 दोन

0.51

 ಮಿಶ್ರ

0.51

overset

0.50

 trzech

0.50

 crabs

0.49

POSITIVE LOGITS

↵↵

0.71

↵↵↵

0.70

</code>

0.59

↵↵↵↵

0.57

↵↵↵↵↵

0.56

</blockquote>

0.55

↵

0.52

 promulg

0.51

.”

0.51

))

0.50

Activations Density 0.001%